The majority of theoretical work in machine learning is done under the assumption of exchangeability: essentially, it is assumed that the examples are generated from the same prob...
Vladimir Vovk, Ilia Nouretdinov, Alexander Gammerm...
We propose VAriable Length Value Encoding (VALVE) technique to reduce the power consumption in the off-chip data buses. While past research has focused on encoding fixed length da...
Dinesh C. Suresh, Banit Agrawal, Walid A. Najjar, ...
This paper describes an efficient implementation of an effective sequential synthesis operation that uses induction to detect and merge sequentially-equivalent nodes. State-encodi...
Alan Mishchenko, Michael L. Case, Robert K. Brayto...
Online boosting is one of the most successful online learning algorithms in computer vision. While many challenging online learning problems are inherently multi-class, online boo...
Amir Saffari, Martin Godec, Thomas Pock, Christian...
In this work, we present a new optical routing framework, O-Router for future low-power on-chip optical interconnect integration utilizing silicon compatible nano-photonic devices...
Duo Ding, Yilin Zhang, Haiyu Huang, Ray T. Chen, D...